Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

step and acc #5

Open
zzjss12 opened this issue May 6, 2023 · 15 comments
Open

step and acc #5

zzjss12 opened this issue May 6, 2023 · 15 comments

Comments

@zzjss12
Copy link

zzjss12 commented May 6, 2023

  1. May I ask how to adjust the following three values when the data volume changes?
    step_ per_ epoch,valid_ step_ per_ epoch,test_ step_ per_ epoch

  2. What is the reason why the ACC value has been around 50%?

@zzjss12
Copy link
Author

zzjss12 commented Jun 5, 2023

image
这里面的 graph_embedding = tf.reduce_sum(curr_embedding, axis=2) curr_embedding 这个变量应该是prev_embedding吧

@zzjss12
Copy link
Author

zzjss12 commented Jun 6, 2023

image
The threshold here should be 0.5. The problem has been resolved.

@Hululuhh
Copy link

Hululuhh commented Jan 6, 2024

  1. May I ask how to adjust the following three values when the data volume changes?
    step_ per_ epoch,valid_ step_ per_ epoch,test_ step_ per_ epoch
  2. What is the reason why the ACC value has been around 50%?

请问你成功复现了吗,可以交流一下吗

@Yunlongs
Copy link
Owner

Yunlongs commented Jan 9, 2024

@Hululuhh 请问你遇到同样的问题了吗?

@Hululuhh
Copy link

Hululuhh commented Jan 9, 2024

@Hululuhh 请问你遇到同样的问题了吗?

对的,我还发现使用您的数据训练过程中valid的auc一直为0,导致没有模型保存,这是为什么?感谢您,如果方便的话,[email protected]是我的邮箱,我希望可以得到您的帮助

@Yunlongs
Copy link
Owner

Yunlongs commented Jan 9, 2024

@Hululuhh 你这边方便把zzjss12同学所说的threshold改为0.5然后再看下问题是否存在吗?这有可能是我之前更新代码产生的bug,谢谢

@Hululuhh
Copy link

Hululuhh commented Jan 9, 2024 via email

@Hululuhh
Copy link

@Hululuhh 你这边方便把zzjss12同学所说的threshold改为0.5然后再看下问题是否存在吗?这有可能是我之前更新代码产生的bug,谢谢

我修改了,看起来train的Accuracy会到75左右,但valid和test还是40,并且auc为0

@Yunlongs
Copy link
Owner

@Hululuhh 那看起来threshold的值是0.5时训练才是正确的。AUC值为0,可能是代码里的计算方式有问题

@iDTer
Copy link

iDTer commented Apr 16, 2024

@Hululuhh 那看起来threshold的值是0.5时训练才是正确的。AUC值为0,可能是代码里的计算方式有问题

image
valid代码中加上这行好像就可以了

@qrzbing
Copy link

qrzbing commented Apr 24, 2024

哈喽各位大佬,请问你们是怎么解决保存模型时报错

ValueError: Model <__main__.MyModel object at 0x000001CD174F7D88> cannot be saved because the input shapes have not been set. Usually, input shapes are automatically determined from calling .fit() or .predict(). To manually set the shapes, call model._set_inputs(inputs).

的问题的呀

@chen5990
Copy link

  1. May I ask how to adjust the following three values when the data volume changes?
    step_ per_ epoch,valid_ step_ per_ epoch,test_ step_ per_ epoch
  2. What is the reason why the ACC value has been around 50%?

请问你成功复现了吗,可以交流一下吗

您好,请问你们用的train文件以及valid文件都是啥呢?我看readme里头也没有说明

@chen5990
Copy link

@Hululuhh 那看起来threshold的值是0.5时训练才是正确的。AUC值为0,可能是代码里的计算方式有问题

您好,请问训练时用的train文件以及valid文件都是啥呢?我看readme里头也没有说明

@chen5990
Copy link

image The threshold here should be 0.5. The problem has been resolved.

您好,请问训练时用的train文件以及valid文件都是啥呢?我看readme里头也没有说明

@chen5990
Copy link

@Hululuhh 那看起来threshold的值是0.5时训练才是正确的。AUC值为0,可能是代码里的计算方式有问题

image valid代码中加上这行好像就可以了

您好,请问训练时用的train文件以及valid文件都是啥呢?我看readme里头也没有说明

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants